Unverified50% confidenceFactExact time
Llama 3 70B量化版（Q4精度）仍需约35GB内存
1
Sources
50%
Confidence
Long-term
Relevance
7/23/2026
First Seen
Sources
Related Claims
UnverifiedFor a model of approximately 160 GB (such as the UD-Q3_K_XL quantized version of Qwen3.5-397B), running the lens requires approximately 20 GB of additional memory.80% similarUnverifiedModels in the 3B–4B range, such as Qwen2.5 3B or Llama 3.2 3B, require only 2 to 2.5GB of VRAM under Q4 quantization.78% similarVerifiedThe Qwen2.5:7B model is approximately 4 GB in size after Q4 quantization.78% similarUnverifiedA 70B model can be compressed to approximately 35GB at INT4 precision.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/594381API
curl https://kongchang.com/api/v1/knowledge/claims/594381MCP
get_claim(id=594381)